Dataset Versions

v6

2023-05-03 2:49pm

Generated on May 3, 2023

Dataset Split

Train Set 87%
186Images
Valid Set 8%
17Images
Test Set 5%
10Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 1 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Exposure: Between -5% and +5%
Blur: Up to 0.25px